初始化项目,由ModelHub XC社区提供模型

Model: zhuojing-huang/gpt2-spanish-english-configC-1-EWC-frzn_emb
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-29 19:33:53 +08:00
commit 94ee2da79c
11 changed files with 150901 additions and 0 deletions

32
tokenizer_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 256,
"pad_token": "<|endoftext|>",
"special_tokens": [
"<|endoftext|>"
],
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<unk>"
}